Job Details:Job Description: We are looking for a dynamic and passionate senior contributor to work in Intel''s AI Group. Day-to-day work involves working on Open source AI Frameworks such as PyTorch focusing on inference serving frameworks like vLLM and SGLang. The job role involves design , developing and optimizing features for Intel''s AI frameworks software stack for Intel''s AI accelerators and next generation GPUs.The roles and responsibilities that you would need to performance may include the following: Design and develop SW features for AI frameworks - both HW-agnostic and HW-aware feature. Enhance and extend the Deep learning training, and Inference capabilities in the Software stack. Analysing and architecting of state of the art features across different frameworks and drive development across full software stack. Identifying optimization opportunities in the software stack to enhance performance of Deep learning workloads Participate in discussions with Open-source community, involve in development, adopting upstream and Upstream software.
Qualifications:BTech or MS/MTech in CS, ECE or related fields with an overall experience of 6 to 12 years. Proficient in Python based complex software implementations. Intermediate knowledge of advanced C++ (C++ 14/17) and parallel programming. In depth and hands on experience in one of the frameworks such as PyTorch, vLLM and SGLang In depth knowledge of LLMs Practical knowledge of Deep Learning models for image , video generation is desirable Ability to debug complex issues in multi layered SW systems. Understanding of SW integration in large open-source frameworks. Strong understanding of computer architecture and HW-SW optimization techniques. Effective communication skills and experience with working in a cross-geo teams. Performance analysis of code on both host and accelerators/GPUs using open-source and proprietary profilersPreferable Experience in developing and integrating CUTLASS or Triton based kernels like GEMM, Convolution, Flash attention etc Knowledge of compiler algorithms for heterogeneous system and Fuser optimizations.
Job Type:Experienced Hire
Shift:Shift 1 (India)
Primary Location: India, Bangalore
Business group:As a member of the Chief Technology Office, Artificial Intelligence, and Network and Edge Group (CTO AI NEX), you will be committed to strategically penetrating the AI market by delivering disruptive and transformative solutions. Your focus will be on leveraging technology innovation and incubation to drive commercial success, ensuring that advancements create significant value. The team is dedicated to driving the software-defined transformation of the world''s networks profitably, setting new standards for efficiency and connectivity. Through these priorities, you aim to lead the way in technological evolution and redefine the future of global networks.
Work Model for this Role
This role will be eligible for our hybrid work model which allows employees to split their time between working on-site at their assigned Intel site and off-site. * Job posting details (such as work model, location or time type) are subject to change.
